© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40007
    Prev
    Next
    INDEX
    Explanations

    good technicians, squat, suitable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    0.63
    ské
    0.52
    רי
    0.50
     Kiến
    0.49
     dici
    0.47
    can
    0.46
     can
    0.46
    的过程中
    0.46
    Databaze
    0.45
    rid
    0.44
    POSITIVE LOGITS
    してください
    0.47
    ι
    0.45
     simplic
    0.44
    次回
    0.44
    трон
    0.44
    記
    0.44
    য়ন
    0.43
     факторов
    0.43
     Виктор
    0.43
     зависит
    0.43
    Activations Density 0.000%

    No Known Activations